Equipment and method for detecting key word in continuous speech

Abstract

The invention discloses equipment and a method for detecting a key word in continuous speech. The equipment comprises an input device, an identification device, a prosodic feature extraction device, a prosodic word boundary determination device, a confidence adjustment device, a judgment device and an output device, wherein the input device is used for inputting the continuous speech; the identification device is used for identifying a candidate key word from the continuous speech, giving out corresponding confidence, and identifying filling sounds included in the continuous speech; the prosodic feature extraction device is used for extracting prosodic features related with adjacent specific filling sounds; the prosodic word boundary determination device is used for determining the boundary between the adjacent specific filling sounds to be the probability of the prosodic word boundary according the prosodic features; the confidence adjustment device is used for adjusting the confidence of the candidate key word according to the boundary which is between the adjacent specific filling sounds included in a speech segment corresponding to the candidate key word and serves as the probability of the prosodic word boundary; the judgment device is used for judging whether the adjusted confidence of the candidate key word is higher than a preset threshold value; and the output device is used for outputting the candidate key word which has the adjusted confidence higher than the preset threshold value and serves as the key words.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a device and method for detecting keywords in continuous speech. Background technique [0002] Among the various communication methods of human beings, speech undoubtedly occupies the most important position. Since the invention of the computer in the middle of the last century, as it has entered the field of daily life, people hope to use voice as a means of human-computer interaction. Compared with input methods such as keyboards, mice, buttons, and touch, and output methods such as monitors and printers, it is more convenient and friendly for users to interact through voice. In terms of the flow of information, voice-human-computer interaction consists of two parts. One is that the computer recognizes human natural language as information that can be processed, and the other is that the computer converts the returned information into natural and easy-to-understand ...

AI Technical Summary

Problems solved by technology

Compared with using a single threshold, the above methods can reduce the average error rate of the system

[0007] However, the above methods all reduce the error rate by adjusting the receiving threshold, and the essence of the problem is that the confidence calculated by the traditional method only using the acoustic model scoring is not reliable.

Images